Unlock instant, AI-driven research and patent intelligence for your innovation.

Data management method based on k neighborhood nonlinear state estimation algorithm

A nonlinear state and estimation algorithm technology, applied in complex mathematical operations and other directions, can solve problems such as difficult maintenance, time-consuming and labor-intensive neural network models, etc.

Pending Publication Date: 2019-08-23
孙力勇
View PDF2 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Adopting neural network models is usually extremely time-consuming and difficult to maintain in the long run

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Data management method based on k neighborhood nonlinear state estimation algorithm
  • Data management method based on k neighborhood nonlinear state estimation algorithm
  • Data management method based on k neighborhood nonlinear state estimation algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] The present invention is a data governance method based on a k-neighborhood nonlinear state estimation algorithm, such as figure 1 as shown, figure 1 It is the construction process memory matrix diagram of the present invention, and the method comprises the following steps:

[0053] Step 1: Generate historical observation vector set D.

[0054] The historical data used to generate the historical observation vector set K should meet the following requirements:

[0055] (1) Covers a sufficiently long period of operation;

[0056] (2) Each set of data expresses a normal state of the target object;

[0057] (3) To satisfy the simultaneity of each variable in each group of sampling values, it must be the sampling values ​​at the same time.

[0058]

[0059] Among them, m represents m normal data of a certain object, which means that there are m times when the device is sampled in a certain period of time; n means that a certain object has n related data, which means...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention belongs to the technical field of basic platform data management in the power industry, and particularly relates to a data management method based on a k neighborhood nonlinear state estimation algorithm. The method comprises the following steps: generating a historical observation vector set D; performing data normalization processing; constructing a process memory matrix; mathematical model and computational process. According to the method, a primary system diagram is used to associate data of electrical apparatus elements, correlation of task data can be obtained from a macroscopic level, and a k neighborhood nonlinear state estimation algorithm is used to govern power grid data; according to the invention, the error checking and the error correction of the blower fan report data can be realized.

Description

technical field [0001] The invention belongs to the technical field of data governance of basic platforms in the electric power industry, and in particular relates to a data governance method based on a k-neighborhood nonlinear state estimation algorithm. Background technique [0002] At present, the literature and technology of "data governance" mainly focus on the state estimation of individual wind turbines and lines, and there is no universality for correcting and sorting the production data of the entire regional power grid. Cooperate with the primary system map of Liaoning Province, such as figure 2 , the state model of any wind turbine in the whole network can be established, and the state estimation and correction of the state of the wind turbine can be carried out according to the state model. The wiring model in the primary system diagram can be formed as a tree diagram, and the data structure after abstraction is a tree structure. [0003] Neural network modelin...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F17/16G06F17/18
CPCG06F17/16G06F17/18
Inventor 孙力勇
Owner 孙力勇